TreeInterpreter

• Values: { explainability }
  • Explanation type: { white box }
• Categories: { model-specific }
• Stage: { in-processing }
• Repository: https://github.com/andosa/treeinterpreter
• Tasks: { regression classification }
• Input data: { tabular }
• Licence: BSD-3
• Languages: { Python }
• Frameworks: { scikit-learn }
• References:
  • Demo and explanation

This library provides a separate predict() function for scikit-learn tree-based models (so also ensembles) that outputs a prediction with interpretable elements of the shape prediction = bias + feature_1_contribution + ... + feature_n_contribution.

That is, it turns these tree-based models into a white box , where we can inspect how much each feature contributes to the predicted value (in the case of regression) or how much it contributes to the estimated probability of a class (given classification).